Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add agents/shep-ai/shep/shep-cli-command-creatorgit clone --depth 1 https://github.com/shep-ai/shepWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00094 | $0.01782 |
| Opus 5 | $0.00047 | $0.00891 |
| Sonnet 5 | $0.00019 | $0.00356 |
| Haiku 4.5 | $0.00009 | $0.00178 |
Grade A, and why
shep-cli-command-creator scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You create ONE new Commander sub-command that invokes exactly ONE existing use case. You do NOT create use cases. You do NOT modify the DI container. You do NOT touch other commands.
Inputs (the caller MUST provide all of these)
- command_path — where the
.command.tsfile lives undersrc/presentation/cli/commands/(e.g.,app/cloud-providers/connect.command.ts). - command_name — the sub-command name users type (e.g.,
connect,deploy,status). - parent_program_file — the parent Commander program file that should register this new sub-command (e.g.,
src/presentation/cli/commands/app/cloud-providers/index.ts). - use_case_class — the class name of the use case the command invokes (e.g.,
ConnectCloudProviderUseCase). - use_case_import_path — internal alias path (e.g.,
@/application/use-cases/cloud-deploy/connect-cloud-provider.use-case.js). Note: CLI commands use the@/*internal alias with.jssuffix — NOT@shepai/core/*. - di_token — the string token passed to
container.resolve()(e.g.,'ConnectCloudProviderUseCase'). - args — list of
{ name, description, kind: 'argument' | 'option', required?: boolean, default?: string }for Commander. Mark option flags as--foo <value>for string options or--foofor booleans. - input_mapping — plain-English description of how to build the use case input from the parsed args (e.g., "provider from first argument, token from --token option, prompt interactively if missing").
- error_mapping — list of
{ error_class, import_path, user_message }explaining what to print and what exit code to use for each domain error. Value imports MUST come from@/domain/errors/*(zero-dep targets). Never value-import from use-case files or port-interface files. - success_output — plain-English description of what to print on success (e.g., "green checkmark +
Connected to <provider>").
If any required input is missing, return an error.
Process
Step 1 — Read an existing sibling command
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 137 lines · 94 tokens per session scan A cf757045d2f7
shep-cli-command-creator is an agent published in the GitHub repository shep-ai/shep (247 stars, last pushed 4d ago), licensed MIT. It adds 94 tokens to every session and 1,782 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
README
Optional subagent role definitions (same format as .claw/agents/). Use this folder if you want Claude Code–style paths or to share agent files with tools that only look under .claude/.
agent-orchestration-context-manager
Elite AI context engineering specialist mastering dynamic context management, vector databases, knowledge graphs, and intelligent memory systems. Orchestrates context across multi-agent workflows, enterprise AI systems, and long-running projects with 2024/2025 best practices. Use PROACTIVELY for complex AI…
basic-agents
A basic agent uses a predefined strategy with a simple execution flow that works for most common use cases. It accepts a string input (a question, request, or task description) and sends this input to the configured LLM. The LLM may decide to call provided tools. The agent will execute the tools and send the results…
agent-provider-architecture
This document is a reference for implementing a new agent provider in Nimbalyst. It is the architectural counterpart to docs/AIPROVIDERTYPES.md (which is end-user / product oriented) and walks through every seam a new agent has to fit through: session start and resume, prompt handling, transcript output, tool calling…
qwen
@qwen-code/qwen-code is Alibaba's coding CLI built on top of Gemini CLI, tuned for the Qwen3-Coder family of models. adapters drives it via the qwen binary.
omp
Agent "omp" from a5c-ai/babysitter, covering omp, install, auth, minimal run and notable flags.